YuJungSoo commited on
Commit
c63929b
1 Parent(s): 2b4297a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - custom_squad_v2
6
+ model-index:
7
+ - name: kobigbird-pure45-28788823
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # kobigbird-pure45-28788823
15
+
16
+ This model is a fine-tuned version of [monologg/kobigbird-bert-base](https://huggingface.co/monologg/kobigbird-bert-base) on the custom_squad_v2 dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 4.5214
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
+ - seed: 45
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 256
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - num_epochs: 3
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 0.84 | 4 | 5.2857 |
53
+ | No log | 1.84 | 8 | 4.6361 |
54
+ | No log | 2.84 | 12 | 4.5214 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.25.1
60
+ - Pytorch 1.13.0+cu116
61
+ - Datasets 2.8.0
62
+ - Tokenizers 0.13.2